janus/janusflow/models/processing_vlm.py [348:404]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

        return prepare

    def __call__(
        self,
        *,
        prompt: str = None,
        conversations: List[Dict[str, str]] = None,
        images: List[Image] = None,
        force_batchify: bool = True,
        **kwargs,
    ):
        """

        Args:
            prompt (str): the formatted prompt;
            conversations (List[Dict]): conversations with a list of messages;
            images (List[ImageType]): the list of images;
            force_batchify (bool): force batchify the inputs;
            **kwargs:

        Returns:
            outputs (BaseProcessorOutput): the output of the processor,
                - input_ids (torch.LongTensor): [N + image tokens]
                - images (torch.FloatTensor): [n_images, 3, H, W]
                - image_id (int): the id of the image token
                - num_image_tokens (List[int]): the number of image tokens
        """

        prepare = self.process_one(
            prompt=prompt, conversations=conversations, images=images
        )

        if force_batchify:
            prepare = self.batchify([prepare])

        return prepare

    def batchify(
        self, prepare_list: List[VLChatProcessorOutput]
    ) -> BatchedVLChatProcessorOutput:
        """
        Preprocesses the inputs for multimodal inference.

        Args:
            prepare_list (List[VLChatProcessorOutput]): A list of VLChatProcessorOutput.

        Returns:
            BatchedVLChatProcessorOutput: A dictionary of the inputs to use for multimodal inference.
        """

        batch_size = len(prepare_list)
        sft_format = []
        n_images = []
        seq_lens = []
        for prepare in prepare_list:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



janus/models/processing_vlm.py [318:374]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

        return prepare

    def __call__(
        self,
        *,
        prompt: str = None,
        conversations: List[Dict[str, str]] = None,
        images: List[Image] = None,
        force_batchify: bool = True,
        **kwargs,
    ):
        """

        Args:
            prompt (str): the formatted prompt;
            conversations (List[Dict]): conversations with a list of messages;
            images (List[ImageType]): the list of images;
            force_batchify (bool): force batchify the inputs;
            **kwargs:

        Returns:
            outputs (BaseProcessorOutput): the output of the processor,
                - input_ids (torch.LongTensor): [N + image tokens]
                - images (torch.FloatTensor): [n_images, 3, H, W]
                - image_id (int): the id of the image token
                - num_image_tokens (List[int]): the number of image tokens
        """

        prepare = self.process_one(
            prompt=prompt, conversations=conversations, images=images
        )

        if force_batchify:
            prepare = self.batchify([prepare])

        return prepare

    def batchify(
        self, prepare_list: List[VLChatProcessorOutput]
    ) -> BatchedVLChatProcessorOutput:
        """
        Preprocesses the inputs for multimodal inference.

        Args:
            prepare_list (List[VLChatProcessorOutput]): A list of VLChatProcessorOutput.

        Returns:
            BatchedVLChatProcessorOutput: A dictionary of the inputs to use for multimodal inference.
        """

        batch_size = len(prepare_list)
        sft_format = []
        n_images = []
        seq_lens = []
        for prepare in prepare_list:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -